diff --git a/.gitattributes b/.gitattributes
index 213696d2e3bfed163e0bbe2e8516489193cb5a43..8b5a0ca6460595054c5d597c8f9594184ca9d0d0 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -121,3 +121,4 @@ data/AB/1954/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1955/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1956/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1957/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1958/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/d6c84bb94ee54896bd6383b27ae16418_python.cwl b/.renku/workflow/d6c84bb94ee54896bd6383b27ae16418_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..b5c8da9051de046dfbd8d1fb9f0c16246023d865
--- /dev/null
+++ b/.renku/workflow/d6c84bb94ee54896bd6383b27ae16418_python.cwl
@@ -0,0 +1,51 @@
+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_origxml.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/AB/1958/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1958/02_extractedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_3)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1958
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1958/02_extractedxml.tar.gz b/data/AB/1958/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d231448d1104fcbfbe056b7d53f252e577c766a3
--- /dev/null
+++ b/data/AB/1958/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3128d169f30766a379fa27c32d201bcf8b660b3c7554550b4ff854144bdda0
+size 103028843